Aging buildings and warehouses require reliable structural health monitoring to ensure integrity and minimize risk of failure. Cracks in building components are often an initial indication of structural distress, raising concerns among occupants over the risk of failure. To address the concerns, various non-destructive testing (NDT) approaches such as rebound hammer, ultra-sonic pulse velocity and visual inspection are used. The present study aimed to develop a structural condition index integrating all the available NDT approaches to analyze the structural stability of the buildings. An extensive methodology is developed by conducting the NDT’s which includes rebound hammer, ultra-sonic pulse velocity and the Visual inspection, later these are assessed with the Degree, Extent, Relevance (DER) approach to yield the condition index (CI). The CI is a quantifiable metric for prioritizing maintenance operations. After determining the current structure’s condition index, the principal component approach (PCA) will be adopted to conduct a statistical analysis which will enable the extraction of key patterns and correlations within the dataset, reducing dimensionality and facilitating a straightforward interpretation of the structural and energy-related variables. Also, different machine learning methods for segmentation were looked at, and the Random Forest Algorithm (RFA) and Support Vector Machine (SVM) were performed in this case. Based on the results it was concluded that SVM was the best fit for this type of assessment. By providing a comprehensive understanding of a structure’s health, this approach empowers proactive mitigation strategies. Through targeted interventions based on the CI and insightful data analysis, building lifespans can be extended and potential failures can be averted.